Recommendation Systems

What I Learned From Arize:Observe 2022

What I Learned From Arize:Observe 2022

Last month, I had the opportunity to speak at Arize:Observe, the first conference dedicated solely to ML observability from both a business and technical perspective. More than a mere user conference, Arize:Observe features presentations and panels from industry thought leaders and ML teams across sectors. Designed to tackle both the basics and most challenging questions and use cases, the conference has sessions about performance monitoring and troubleshooting, data quality and drift monitoring and troubleshooting, ML observability in the world of unstructured data, explainability, business impact analysis, operationalizing ethical AI, and more.

In this blog recap, I will dissect content from the summit’s most insightful technical talks, covering a wide range of topics from scaling real-time ML and best practices of effective ML teams to challenges in monitoring production ML pipelines and redesigning ML platform.

What I Learned From Attending MLOps World 2021

What I Learned From Attending MLOps World 2021

Two months ago, I attended the second edition of MLOps: Production and Engineering World, which is a multi-day virtual conference organized by the Toronto Machine Learning Society that explores the best practices, methodologies, and principles of effective MLOps. In this post, I would like to share content from the talks that I found most useful during this conference, broken down into Operational and Technical talks.

Datacast Episode 66: Monitoring Models in Production with Emeli Dral

Datacast Episode 66: Monitoring Models in Production with Emeli Dral

Emeli Dral is a Co-founder and CTO at Evidently AI, a startup developing tools to analyze and monitor the performance of machine learning models. Earlier, she co-founded an industrial AI startup and served as the Chief Data Scientist at Yandex Data Factory. She led over 50 applied ML projects for various industries - from banking to manufacturing. Emeli is also a data science lecturer at St. Petersburg State Management School and Harbour.Space University. She is a co-author of the Machine Learning and Data Analysis curriculum at Coursera with over 100,000 students. She also co-founded Data Mining in Action, the largest open data science course in Russia.

Datacast Episode 65: Chaos Theory, High-Frequency Trading, and Experimentations at Scale with David Sweet

Datacast Episode 65: Chaos Theory, High-Frequency Trading, and Experimentations at Scale with David Sweet

David Sweet was a quantitative trader at GETCO, where he used experimental methods to tune trading strategies, and a machine learning engineer at Instagram, where he experimented on a large-scale recommender system. He is currently writing a book called "Tuning Up," an extension of lectures given at NYU Stern on tuning high-frequency trading systems. Before working in the industry, he received a Ph.D. in Physics and published research in Physical Review Letters and Nature. The latter publication – an experiment demonstrating chaos in geometrical optics -- has become a source of inspiration for computer graphics artists, undergraduate Physics instructors, and an exhibit called TetraSphere at the Museum of Mathematics in New York City.

Recommendation System Series Part 8: The 14 Properties To Take Into Account When Evaluating Real-World Recommendation Systems

Recommendation System Series Part 8: The 14 Properties To Take Into Account When Evaluating Real-World Recommendation Systems

Various properties are commonly considered when choosing the recommendation approach, whether for offline or online scenarios. These properties have trade-offs, so it is critical to understand and evaluate their effects on the overall performance and the user experience. This blog post is my attempt to summarize these properties succinctly.

Datacast Episode 48: AI Ethics, Open Data, and Recommendations Fairness with Jessie Smith

Datacast Episode 48: AI Ethics, Open Data, and Recommendations Fairness with Jessie Smith

Jessie J. Smith (Jess) is a second-year Ph.D. student in the Department of Information Science at the University of Colorado Boulder. Her Ph.D. research focuses on AI ethics, machine learning fairness and bias, and ethical speculation in the computer science classroom. Since receiving her Bachelor's in Software Engineering, Jess works to engage in public scholarship about her research to encourage transparency and interdisciplinary dialogue about technology's unintended consequences. She is also the co-host and co-creator of The Radical AI Podcast.

Datacast Episode 46: From Building Recommendation Systems To Teaching Online Courses with Frank Kane

Datacast Episode 46: From Building Recommendation Systems To Teaching Online Courses with Frank Kane

Frank Kane is the owner of Sundog Education, teaching machine learning and data science online to over 500,000 students worldwide. Before Sundog, Frank spent nine years at Amazon as a senior engineer and senior manager, specializing in recommender systems and running IMDb's engineering department. Frank also worked in the early days of video game development, dating back to the adventure games of Sierra Online in the early '90s, and has also developed computer graphics software for flight simulators and military simulators around the world. Today Frank is focused on the world of online education, living in the Orlando Florida area with his family.

Datacast Episode 41: Effective Data Science with Eugene Yan

Datacast Episode 41: Effective Data Science with Eugene Yan

Eugene Yan is a data scientist and writer. He works at the intersection of consumer data & tech to build machine learning systems to help customers and writes about effective data science, learning, and career. He's currently an Applied Scientist at Amazon, helping users read more and get more out of reading. Previously, he led the data science team at Lazada (acquired by Alibaba in 2016), working on e-commerce ML systems (e.g., ranking, automation, fraud detection).

Recommendation System Series Part 7: The 3 Variants of Boltzmann Machines for Collaborative Filtering

Recommendation System Series Part 7: The 3 Variants of Boltzmann Machines for Collaborative Filtering

In this post and those to follow, I will be walking through the creation and training of recommendation systems, as I am currently working on this topic for my Master Thesis. Part 7 explores the use of Boltzmann Machines for collaborative filtering. More specifically, I will dissect three principled papers that incorporate Boltzmann Machines into their recommendation architecture. But first, let’s walk through a primer on Boltzmann Machine and its variants.

Recommendation System Series Part 6: The 6 Variants of Autoencoders for Collaborative Filtering

Recommendation System Series Part 6: The 6 Variants of Autoencoders for Collaborative Filtering

In this post and those to follow, I will be walking through the creation and training of recommendation systems, as I am currently working on this topic for my Master Thesis. In Part 6, I explore the use of Auto-Encoders for collaborative filtering. More specifically, I will dissect six principled papers that incorporate Auto-Encoders into their recommendation architecture.